{"total":57,"rows":[{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54,"area":null},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2107.05545","title":"Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing","created":"2021-07-12","cited_by_count":23,"area":null},{"id":"2111.09858","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","created":"2021-11-18","cited_by_count":23,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2110.14457","title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching","created":"2021-10-27","cited_by_count":19,"area":null},{"id":"2202.03466","title":"Reward-Respecting Subtasks for Model-Based Reinforcement Learning","created":"2022-02-07","cited_by_count":16,"area":null},{"id":"2112.15025","title":"Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates","created":"2021-12-30","cited_by_count":14,"area":null},{"id":"2310.10833","title":"Proper Laplacian Representation Learning","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2210.13153","title":"Reachability-Aware Laplacian Representation in Reinforcement Learning","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2307.11629","title":"Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2203.11369","title":"Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2103.02650","title":"Successor Feature Sets: Generalizing Successor Representations Across Policies","created":"2021-03-03","cited_by_count":6,"area":null},{"id":"2302.00671","title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing","created":"2023-02-01","cited_by_count":6,"area":null},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2202.03597","title":"Local Explanations for Reinforcement Learning","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2201.08227","title":"Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs","created":"2022-01-20","cited_by_count":4,"area":null},{"id":"2311.03534","title":"PcLast: Discovering Plannable Continuous Latent States","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2402.06590","title":"Predictive representations: building blocks of intelligence","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2503.19007","title":"Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2205.12515","title":"Toward Discovering Options that Achieve Faster Planning","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2207.09897","title":"Successor Representation Active Inference","created":"2022-07-20","cited_by_count":3,"area":null},{"id":"2305.18491","title":"Towards a Better Understanding of Representation Dynamics under TD-learning","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2401.09491","title":"Memory, Space, and Planning: Multiscale Predictive Representations","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2206.03467","title":"Discrete State-Action Abstraction via the Successor Representation","created":"2022-06-07","cited_by_count":1,"area":null},{"id":"2306.05298","title":"Habits of Mind: Reusing Action Sequences for Efficient Planning","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2406.03845","title":"Open Problem: Active Representation Learning","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2501.12668","title":"NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2502.03405","title":"Deep Clustering via Probabilistic Ratio-Cut Optimization","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2201.01836","title":"A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2206.04993","title":"The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2301.00009","title":"On the Geometry of Reinforcement Learning in Continuous State and Action Spaces","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2306.04902","title":"A Cover Time Study of a non-Markovian Algorithm","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2510.21952","title":"Revisiting Orbital Minimization Method for Neural Operator Decomposition","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2603.20103","title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2609.05104","title":"Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05508","title":"When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}